In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
This paper considers the remote interactive browsing of large JPEG2000 images. In contrast with previous contributions, we focus on the dynamic nature of the system. Practically, ...
Antonin Descampe, Benoit M. Macq, Christophe De Vl...
In this paper, we proposed a neural network based scheme for performing unsupervised video object segmentation, especially for videophone or videoconferencing applications. The pr...
Anastasios D. Doulamis, Nikolaos D. Doulamis, Stef...
Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge ...
We explore dynamic shaping to integrate our prior beliefs of the final policy into a conventional reinforcement learning system. Shaping provides a positive or negative artificial...